hanzo-dev
be98e205c7
- Crate README + Cargo description: accurate multi-backend framing (was 'Minimalist ML framework.'). - Monochrome badges (drop blue); branding voice + GB10/DGX-Spark unified-memory + Hanzo AI (hanzo.ai). - Fix candle->hanzo rename damage: self-refs github.com/huggingface/hanzo -> github.com/hanzoai/ml; doc-site links -> repo; restore blindly-mangled EXTERNAL author assets to real upstream (lmz/candle-*, Narsil/candle-examples, jbochi/candle-coedit-quantized, HF documentation-images/candle) so example downloads work again. - Legit external HF refs (safetensors, tokenizers, meta-llama, openai/whisper, etc.) left intact.
hanzo-ml-yolo-v8: Object Detection and Pose Estimation
This is a port of Ultralytics YOLOv8. The implementation is based on the tinygrad version and on the model architecture described in this issue. The supported tasks are object detection and pose estimation.
You can run this model in your browser via the YOLOv8 WASM example. The model then fully runs in your browser using WebAssembly - if you use a custom image it will never leave your phone/computer!
Running some example
Object Detection
cargo run --example yolo-v8 --release -- hanzo-ml-examples/examples/yolo-v8/assets/bike.jpg
This prints details about the detected objects and generates a bike.pp.jpg file.
Image source: wikimedia.
Pose Estimation
cargo run --example yolo-v8 --release -- \
hanzo-ml-examples/examples/yolo-v8/assets/bike.jpg --task pose
Command-line flags
--which: select the model variant to be used,n,s,m,l, orxby increasing size and quality.--task:detectfor object detection andposefor pose estimation.--legend-size: the size of the characters to print.--model: use a local model file rather than downloading it from the hub.